AI RESEARCH

YOSE: You Only Select Essential Tokens for Efficient DiT-based Video Object Removal

arXiv CS.CV

ArXi:2604.27322v1 Announce Type: new Recent advances in Diffusion Transformer (DiT)-based video generation technologies have shown impressive results for video object removal. However, these methods still suffer from substantial inference latency. For instance, although MiniMax Remover achieves state-of-the-art visual quality, it operates at only around 10FPS, primarily due to dense computations over the entire spatiotemporal token space, even when only a small masked region actually requires processing.